Triple

T12919862
Position Surface form Disambiguated ID Type / Status
Subject Hell-Heaven E309087 entity
Predicate narrator P2181 FINISHED
Object Usha E448882 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Usha | Statement: [Hell-Heaven, narrator, Usha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Usha
Context triple: [Hell-Heaven, narrator, Usha]
  • A. Usha chosen
    Usha is a goddess in Hindu mythology, often associated with the dawn and revered as a radiant divine figure.
  • B. Usha
    Usha was an ancient Galilean town that served as a major center of Jewish rabbinic leadership and legal activity during the period of the Sanhedrin in Roman-era Palestine.
  • C. Bharati
    Bharati is an epithet of the Hindu goddess Saraswati, highlighting her role as the divine embodiment of eloquence, learning, and the arts.
  • D. Kshipra
    Kshipra is a sacred river in central India, best known for flowing through the holy city of Ujjain and its importance in Hindu religious traditions and festivals.
  • E. Birla
    Birla is a prominent Indian industrialist family known for its major contributions to business, industry, and philanthropy in India.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971e6d9fc8190b8a5244b26b5f78a completed April 10, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8d39d4c81908fab65129f292862 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 5:41 p.m.